OpenClaw Guide
Security checks across malware telemetry and agentic risk
Overview
The artifacts appear to be coherent ClawHub developer and maintainer skills with disclosed local, GitHub, Convex, and moderation workflows rather than hidden or unrelated behavior.
Install only if you intend to use ClawHub maintainer and Convex development workflows. Review the staff-moderation and autoreview instructions before use: moderation commands can affect real users and published content, and autoreview can run a nested review with broad local authority unless invoked with its safer opt-out flags.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.